Using Gaze Behavior and Head Orientation for Implicit Identification in Virtual Reality
summary
A biometric system uses gaze velocities and head rotation from an HTC Vive + Pupil Labs eye tracker (400×400 @ 120 Hz, 16‑point 3D calibration) while participants follow two moving stimuli on different trajectories. An 11‑participant study (11 complete recordings) yields KNN identification means of ~45% (stimulus 1) and 75% (stimulus 2 with head rotation). Deep learning with 2.5 s sliding windows produces an encoder model: 97% (stimulus 1) and 100% (stimulus 2).
AI-written summary · about
related talks
17mEyeGrip: Detecting Targets in a Series of Uni-directional Moving Objects Using Optokinetic ...
20mBuilding a Personalized, Auto-Calibrating Eye Tracker from User Interactions
19mGazeProjector: Accurate Gaze Estimation and Seamless Gaze Interaction Across ...
19mEveryday Eye Contact Detection Using Unsupervised Gaze Target Discovery
22mPinpointing: Precise Head- and Eye-Based Target Selection for Augmented Reality
21mSelf-Calibrating Head-Mounted Eye Trackers Using Egocentric Visual Saliency
19mEyeScout: Active Eye Tracking for Position and Movement Independent Gaze Interaction with Large ...
16mEye-Trace: Segmentation of Volumetric Microscopy Images with Eyegaze